公开(公告)号：US09449236B2

公开(公告)日：2016-09-20

申请号：US14070812

申请日：2013-11-04

Applicant: Xerox Corporation

Inventor： Yao Rong Wang ,  Orhan Bulan ,  Hengzhou Ding ,  Graham S. Pennington

IPC: H04N7/18 ,  G06K9/00 ,  G08G1/14 ,  G08G1/16

CPC classification number: G06K9/00812 ,  G06K9/00771 ,  G08G1/141 ,  G08G1/168

Abstract: A method for determining parking availability includes receiving video data from a sequence of frames taken from an image capture device monitoring a parking area. The method includes detecting at least one object located in the parking area. The method includes determining boundaries of the parking area. The boundaries include at least an inner boundary relative to the image capture device and an outer boundary relative to the image capture device. The outer boundary is substantially parallel to the inner boundary. The method further includes computing a length of at least one of the object and a space between objects using an object pixel for each of the inner and outer boundaries. Using the computed length, The method includes determining a parking availability in the parking area. The method includes outputting a notice of the parking availability to a user.

Abstract translation: 用于确定停车可用性的方法包括从监视停车区域的图像捕获装置中取出的帧序列中接收视频数据。 该方法包括检测位于停车区域中的至少一个物体。 该方法包括确定停车区域的边界。 边界至少包括相对于图像捕获装置的内边界和相对于图像捕获装置的外边界。 外边界基本上平行于内边界。 该方法还包括使用对于每个内边界和外边界的对象像素来计算对象中的至少一个和对象之间的空间的长度。 使用计算的长度，该方法包括确定停车区域中的停车可用性。 该方法包括向用户输出停车可用性的通知。

公开(公告)号：US20150049918A1

公开(公告)日：2015-02-19

申请号：US13967978

申请日：2013-08-15

Applicant: Xerox Corporation

Inventor： Zhigang Fan ,  Subarna Ghosh ,  Hengzhou Ding

IPC: G06T7/60

CPC classification number: G06T7/0042 ,  G06K2209/03 ,  G06T7/74 ,  G06T2207/20101 ,  G06T2207/20104 ,  H04Q1/136

Abstract: A method of estimating one or more dimensions of a patch panel may include receiving an image of a patch panel that comprises a plurality of ports and one or more gaps, extracting, by a computing device, a region of interest from the received image, detecting, by the computing device, one or more possible port edges from the region of interest, fitting the detected possible port edges to a cross-ratio constancy model to determine a port-to-gap-length ratio associated with the patch panel, using the port-length-to-gap-length ratio to determine a location of one or more final port edges, and determining a location of one or more final ports based on the location of the final port edges.

Abstract translation: 估计接线板的一个或多个维度的方法可以包括接收包括多个端口和一个或多个间隙的接线板的图像，由计算设备从接收到的图像提取感兴趣区域，检测 通过计算设备，来自感兴趣区域的一个或多个可能的端口边缘将检测到的可能的端口边缘拟合到交比率常数模型，以使用该接口面板确定与接插板相关联的端口间隙长度比 端口长度到间隙长度比以确定一个或多个最终端口边缘的位置，以及基于最终端口边缘的位置来确定一个或多个最终端口的位置。

公开(公告)号：US20140313364A1

公开(公告)日：2014-10-23

申请号：US13866506

申请日：2013-04-19

Applicant: XEROX CORPORATION

Inventor： Zhigang Fan ,  Hengzhou Ding ,  Manavender Malgireddy

IPC: H04N5/225

CPC classification number: H04N5/225 ,  G06K9/00664 ,  G06K2209/03

Abstract: A method for processing an image of a patch panel includes: a) receiving an initial image; b) determining multiple ports of the patch panel are aligned in a desired orientation in the initial image; c) processing the initial image to identify edge lines perpendicular to the desired orientation; d) processing the edge lines to identify a port hypothesis that includes an estimated port gap between the multiple ports along the desired orientation and an estimated port size for the multiple ports along the desired orientation; e) processing the port hypothesis to determine an estimated port quantity for the multiple ports; and f) processing the port hypothesis to identify an estimation error between expected and detected edge line positions in relation to a reference axis perpendicular to the edge lines. An apparatus associated therewith includes an input/output and pre-processing modules and detection, hypothesis, estimating, and scoring processors.

Abstract translation: 用于处理接线板的图像的方法包括：a）接收初始图像; b）确定接线板的多个端口在初始图像中以期望的方向对齐; c）处理初始图像以识别垂直于期望取向的边缘线; d）处理边缘线以识别端口假说，其包括沿着期望取向的多个端口之间的估计端口间隙以及沿着期望取向的多个端口的估计端口大小; e）处理端口假设以确定多个端口的估计端口数量; 以及f）处理所述端口假设以识别相对于垂直于所述边缘线的参考轴的期望和检测到的边缘线位置之间的估计误差。 与其相关联的装置包括输入/​​输出和预处理模块以及检测，假设，估计和评分处理器。

公开(公告)号：US20140211023A1

公开(公告)日：2014-07-31

申请号：US13753790

申请日：2013-01-30

Applicant: XEROX CORPORATION

Inventor： Zhigang Fan ,  Hengzhou Ding ,  Yonghui Zhao ,  Shen-Ge Wang

IPC: G06F3/00

CPC classification number: G06K9/2027 ,  G06K9/3233 ,  G06K9/4633 ,  G06T7/13 ,  G06T7/174 ,  G06T2207/10152 ,  G06T2207/20192

Abstract: Methods and systems for detecting an object borderline. A first image with respect to the object can be captured by an image-capturing unit without a flash light and borderlines of the object can be detected. If the detection is successful, the detected borderlines can be outputted. Otherwise, a second image with respect to the object can be captured by the image-capturing unit by applying a flash light and the borderlines can be detected in the image. A geometric transformation between the two images can then be estimated. Finally, the border lines in the first image can be determined by transforming the borderlines detected in the second image. Such an approach effectively detects the appliance borderlines and avoids artifacts caused by applying flash.

Abstract translation: 用于检测物体边界线的方法和系统。 相对于物体的第一图像可以由没有闪光灯的图像拍摄单元捕获，并且可以检测对象的边界线。 如果检测成功，则可以输出检测到的边界线。 否则，可以通过应用闪光灯由图像捕获单元捕获关于对象的第二图像，并且可以在图像中检测边界线。 然后可以估计两个图像之间的几何变换。 最后，可以通过变换在第二图像中检测到的边界来确定第一图像中的边界线。 这种方法有效地检测设备的边界，并避免因应用闪光灯引起的伪影。

公开(公告)号：US20140118560A1

公开(公告)日：2014-05-01

申请号：US13664810

申请日：2012-10-31

Applicant: XEROX CORPORATION

Inventor： Raja Bala ,  Lina Fu ,  Hengzhou Ding

IPC: H04N5/225

CPC classification number: H04N1/00466 ,  H04N1/19594 ,  H04N5/225 ,  H04N5/23293

Abstract: A method and device for aligning an image of a printed substrate using a mobile device. The method includes receiving, by an image capturing device, an image stream of a printed substrate; determining, by a processing device operably connected to the image capturing device, a location and a geometry of the printed substrate from the image stream; displaying, on a display operably connected to the processing device, the image stream; overlaying, by the processing device, at least a first visual marker onto the printed substrate as displayed in the image stream using the location and geometry; and instructing, by the processing device, a user of the mobile device to move the mobile device to align the mobile device and the printed substrate. The device includes the various hardware components configured to perform the method of aligning.

Abstract translation: 一种使用移动装置对准印刷基板的图像的方法和装置。 该方法包括：通过图像捕获装置接收印刷基板的图像流; 通过可操作地连接到所述图像捕获装置的处理装置从所述图像流确定所述印刷基板的位置和几何形状; 在可操作地连接到所述处理装置的显示器上显示所述图像流; 通过处理装置将使用位置和几何形状显示在图像流中的至少第一视觉标记叠加到印刷基板上; 以及由所述处理设备指示所述移动设备的用户移动所述移动设备以对准所述移动设备和所述打印的基板。 该设备包括被配置为执行对准方法的各种硬件组件。

公开(公告)号：US20140056478A1

公开(公告)日：2014-02-27

申请号：US14070775

申请日：2013-11-04

Applicant: Xerox Corporation

Inventor： Zhigang Fan ,  Yonghui Zhao ,  Shen-ge Wang ,  Hengzhou Ding

IPC: G06K9/00

CPC classification number: G06K9/00671 ,  G06K9/2081 ,  G06K9/46

Abstract: A method and apparatus for obtaining an image and providing one or more document files to a user is disclosed. The method may include receiving an image of a target object using an imaging device, analyzing the image to identify one or more features, and accessing a model database to identify an object model having features that match the identified features from the image. When the system determines that more than one model may be a match, the method looks for distinguishing features of the target object and selects a model that includes the distinguishing features. The method then includes, retrieving a document file that corresponds to the identified model from a file database, and providing the document file to a user.

Abstract translation: 公开了一种用于获得图像并向用户提供一个或多个文档文件的方法和装置。 该方法可以包括使用成像设备接收目标对象的图像，分析图像以识别一个或多个特征，以及访问模型数据库以识别具有与来自图像的识别的特征匹配的特征的对象模型。 当系统确定多个模型可能是匹配时，该方法寻找目标对象的区别特征并选择包含区别特征的模型。 该方法然后包括从文件数据库检索对应于所识别的模型的文档文件，并将文档文件提供给用户。